Skip to main content
Glama
Sign In
qmcp

qmcp

by BigKAA
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

qdrant_diff_collection

Compares a Qdrant collection against repository files to detect orphaned vectors, missing files, and modified content, helping keep the vector index in sync with disk.

Instructions

Compare Qdrant collection state with filesystem.

Detects three types of discrepancies:
- orphans: Vectors in Qdrant but file doesn't exist on disk
- missing: Files on disk but not indexed in Qdrant
- modified: Files that exist but content has changed (hash mismatch)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "collection": "<collection>",
      "repo_path": "<repo_path>"
    },
    "name": "qdrant_diff_collection"
  }
}

Input Schema

NameRequiredDescriptionDefault
repo_pathYesRepository path to compare against
collectionYesCollection name to compare

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden. 'Compare' implies a read-only operation and the hash-mismatch definition hints that content hashing occurs (a potentially expensive trait), but the description never explicitly confirms it is side-effect-free, nor does it mention cost on large collections or behavior if the collection is missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One framing sentence followed by a tight three-bullet enumeration; the purpose is front-loaded and every line earns its place by defining a distinct discrepancy category.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read operation with a full output schema, the definition covers what an agent needs to select and invoke it. The remaining gap is operational context — whether it mutates anything, and how it relates to sibling repair/cleanup tools — which is minor given the output schema carries return shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented in the schema. The description adds only implicit framing — that 'collection' is the Qdrant side and 'repo_path' is the filesystem side of the comparison — which is marginal value beyond the schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Compare Qdrant collection state with filesystem') and enumerates the exact three discrepancy categories it reports (orphans, missing, modified). This is far more specific than the sibling names suggest and lets an agent know precisely what the tool produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied — you call it to check consistency between an index and disk — but there is no explicit when-to-use versus siblings such as qdrant_diagnose_collection, qdrant_cleanup, or qdrant_list_indexed_files. No preconditions (collection must exist, repo_path must be a valid indexed directory) or follow-up routing (e.g., use cleanup after diff) are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools